[HBASE-9110] Meta region edits not recovered while migrating to 0.96.0

• Type: Sub-task
• Status: Closed
• Priority: Critical
• Resolution: Fixed
• Affects Version/s: 0.95.2, 0.94.10
• Fix Version/s: 0.98.0, 0.96.0
• Component/s: migration
• Hadoop Flags: Reviewed

Release Note

Adds a step to migration where we split any outstanding WAL files. This process is not distributed so will be slower than the distributed version that runs on cluster startup so, make sure there are few WALs to split at this step by making sure the cluster shutdown is clean pre-upgrade.

• Assignee: Himanshu Vashishtha
• Reporter: Himanshu Vashishtha
• Created: 01/Aug/13 16:05
• Updated: 20/Nov/15 11:54
• Resolved: 29/Aug/13 04:43

Description

I was doing the migration testing from 0.94.11-snapshot to 0.95.0, and faced this issue.

1) Do some edits in meta table (for eg, create a table).

2) Kill the cluster.
(I used kill because we would be doing log splitting when upgrading anyway).

3) There is some dependency on WALs. Upgrade the bits to 0.95.2-snapshot. Start the cluster.
Every thing comes up. I see log splitting happening as expected. But, the WAL-data for meta table is missing.

I could see recovered.edits file for meta created, and placed at the right location. It is just that the new HMaster code tries to recover meta by looking at meta prefix in the log name, and if it didn't find one, just opens the meta region. So, the recovered.edits file, created afterwards, is not honored.

Opening this jira to let folks give their opinions about how to tackle this migration issue.

Issue Links

• is related to: HBASE-8348 Polish the migration to 0.96